set_feature_flag

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false, so the safety profile is covered structurally. The description adds real value beyond that by disclosing latency and mechanism ('takes effect within a second, no deploy'), but it omits critical behavior for a destructive write: that dry_run defaults to true and that a reason is required.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One short, front-loaded sentence with no filler, and the parenthetical adds genuinely useful operational detail. It is arguably undersized for a destructive five-parameter tool, which is a sizing issue rather than wasted verbiage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, non-idempotent mutation with no output schema and zero parameter documentation, the description leaves too much out: the dry_run default that gates whether anything actually happens, why a reason/incident_id is required, and what the effect on live traffic is. Annotations cover safety but not invocation correctness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 5 parameters, so the description carries the full burden and largely fails. The phrase 'on or off' loosely maps to the enabled boolean, but flag, reason, incident_id, and especially dry_run (which defaults to true, meaning a naive call may not actually apply the change) are entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb ('turn on or off') and resource ('feature flag'), so an agent knows exactly what state change is being requested. It does not name any sibling or contrast itself with rollback_service/restart_service, but the action is unambiguous and clearly distinct from the read-oriented siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use guidance, no stated prerequisites, and no mention of alternatives (e.g. flipping a flag vs. rolling back a service). The only contextual hint is 'no deploy', which implies this is the fast path, but the agent is left to infer the situation in which that matters.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.